A Bot Identification Model and Tool Based on GitHub Activity Sequences
This paper was accepted for publication by the Journal on Systems and Software on 18 November 2024 and is already available online.
Abstract. Identifying whether GitHub contributors are automated bots is important for empirical research on collaborative software development practices. Multiple such bot identification approaches have been proposed in the past. In this article, we identify the limitations of these approaches and we propose a new binary classification model, called BIMBAS, to overcome these limitations. To do so, we propose a new ground-truth dataset containing 1,035 bots and 1,115 humans on GitHub. We train BIMBAS on a wide range of features extracted from the activity sequences of these GitHub contributors. We show that the performance of BIMBAS (in terms of precision, recall, F1 score and AUC) is comparable to state-of-the-art bot identification approaches, while being able to identify bots engaged in a wider range of activity types. We implement RABBIT, an open-source command-line bot identification tool based on BIMBAS. We demonstrate its ability to be used at scale, and show that its efficiency outperforms the state-of-the-art.
Fri 7 MarDisplayed time zone: Eastern Time (US & Canada) change
11:00 - 12:30 | Mining Software RepositoriesResearch Papers / Early Research Achievement (ERA) Track / Journal First Track / Reproducibility Studies and Negative Results (RENE) Track at L-1720 Chair(s): Brittany Reid Nara Institute of Science and Technology | ||
11:00 15mTalk | An Empirical Study of Transformer Models on Automatically Templating GitHub Issue Reports Research Papers Jin Zhang Hunan Normal University, Maoqi Peng Hunan Normal University, Yang Zhang National University of Defense Technology, China | ||
11:15 15mTalk | How to Select Pre-Trained Code Models for Reuse? A Learning Perspective Research Papers Zhangqian Bi Huazhong University of Science and Technology, Yao Wan Huazhong University of Science and Technology, Zhaoyang Chu Huazhong University of Science and Technology, Yufei Hu Huazhong University of Science and Technology, Junyi Zhang Huazhong University of Science and Technology, Hongyu Zhang Chongqing University, Guandong Xu University of Technology, Hai Jin Huazhong University of Science and Technology Pre-print | ||
11:30 7mTalk | Uncovering the Challenges: A Study of Corner Cases in Bug-Inducing Commits Early Research Achievement (ERA) Track | ||
11:37 15mTalk | A Bot Identification Model and Tool Based on GitHub Activity Sequences Journal First Track Natarajan Chidambaram University of Mons, Alexandre Decan University of Mons; F.R.S.-FNRS, Tom Mens University of Mons | ||
11:52 15mTalk | Does the Tool Matter? Exploring Some Causes of Threats to Validity in Mining Software Repositories Reproducibility Studies and Negative Results (RENE) Track Nicole Hoess Technical University of Applied Sciences Regensburg, Carlos Paradis No Affiliation, Rick Kazman University of Hawai‘i at Mānoa, Wolfgang Mauerer Technical University of Applied Sciences Regensburg |